ABSTRACT
The majority of patients with prostate cancer die of non-cancer causes of death (COD). It is thus important to accurately predict multi-category COD in these patients. Random forest (RF), a popular machine learning model, has been shown useful for predicting binary cancer-specific deaths. However, its accuracy for predicting multi-category COD in cancer patients is unclear. We included patients in Surveillance, Epidemiology, and End Results-18 cancer registry-program with prostate cancer diagnosed in 2004 (followed-up through 2016). They were randomly divided into training and testing sets with equal sizes. We evaluated prediction accuracies of RF and conventional statistical/multinomial models for 6-category COD by data-encoding types using the 2-fold cross-validation approach. Among 49,864 prostate cancer patients, 29,611 (59.4%) were alive at the end of follow-up, and 5,448 (10.9%) died of cardiovascular disease, 4,607 (9.2%) of prostate cancer, 3,681 (7.4%) of non-prostate cancer, 717 (1.4%) of infection, and 5,800 (11.6%) of other causes. We predicted 6-category COD among these patients with a mean accuracy of 59.1% (n=240, 95% CI, 58.7%-59.4%) in RF models with one-hot encoding, and 50.4% (95% CI, 49.7%-51.0%) in multinomial models. Tumor characteristics, prostate-specific antigen level, and diagnosis confirmation-method were important in RF and multinomial models. In RF models, no statistical differences were found between the accuracies of training versus cross-validation phases, and those of categorical versus one-hot encoding. We here report that RF models can outperform multinomial logistic models (absolute accuracy-difference, 8.7%) in predicting long-term 6-category COD among prostate cancer patients, while pathology diagnosis itself and tumor pathology remain important factors.
ABSTRACT
This community effectiveness randomized clinical trial examined the feasibility and effectiveness of a comprehensive psychosocial treatment, summerMAX, when implemented by a community agency. Fifty-seven high-functioning children (48 male, 9 female), ages 7-12 years with autism spectrum disorder participated in this study. The 5-week summerMAX treatment included instruction and therapeutic activities targeting social/social-communication skills, interpretation of nonliteral language skills, face-emotion recognition skills, and interest expansion. A behavioral program was also used to increase skills acquisition and decrease autism spectrum disorder symptoms and problem behaviors. Feasibility was supported via high levels of fidelity and parent, child, and staff clinician satisfaction. Significant treatment effects favoring the treatment group over waitlist controls were found on all 5 of the primary outcome measures (i.e., child test of nonliteral language skills and parent ratings of the children's autism spectrum disorder symptoms, targeted social/social-communication skills, broader social performance, and withdrawal). Staff clinician ratings substantiated the improvements reported by parents. Results of this randomized clinical trial are consistent with those of prior studies of summerMAX and suggest that the program was feasible and effective when implemented by a community agency under real-world conditions.
